prompt GP ChatGPT

Act as a Senior Codebase Auditor & Tech Debt Refactorer — prompt

Turns an AI assistant into a senior codebase auditor. It pinpoints dead code, redundant logic, and tech debt, delivering a phased refactoring plan.

Open on GitHub

What Act as a Senior Codebase Auditor & Tech Debt Refactorer does

The prompt instructs an AI assistant to act as a senior software engineer auditing code quality and maintainability. It directs the model to inspect eight specific areas: dead code, duplicate logic, orphaned UI components, over-complicated implementations, deprecated patterns, redundant queries, abandoned files, and architectural technical debt. The audit stays strictly analytical.

For every finding, the prompt requires a precise file path, code snippet, rationale, impact level, and regression risk analysis. It organizes the final output into a three-phase cleanup sequence. Phase 1 targets safe zero-risk deletions, Phase 2 handles logic consolidation, and Phase 3 tackles architectural migrations. Because the instructions demand exact file locations, providing the directory tree or code snippets in the chat is required.

What it helps with

spot dead code, unused imports, and abandoned files
isolate duplicate logic and unnecessarily complex implementations
identify redundant database queries and N+1 query risks
construct a three-phase cleanup plan with regression risk ratings

Example prompts for the agent

Please analyze the following codebase details and perform the code quality review: [insert repository structure]
Inspect this file for dead code and duplicate logic: [insert code snippet]
Generate a phased cleanup plan for this component: [insert code]

How to install Act as a Senior Codebase Auditor & Tech Debt Refactorer

How to use

Paste the text at the start of a chat or into project instructions

Manually: put the files in place

.claude/commands/prompts.csv.md

Questions about Act as a Senior Codebase Auditor & Tech Debt Refactorer

How to install Act as a Senior Codebase Auditor & Tech Debt Refactorer in ChatGPT?

No installation command is needed. Copy the prompt text directly into ChatGPT or Claude.ai as your first message, then supply your directory tree or source code.

What does this prompt review in a repository?

It audits eight categories: dead code, duplicate logic, unused UI files, over-complicated code, deprecated patterns, redundant queries, abandoned files, and code smells. Each issue includes risk and impact assessments.

How does the prompt structure the cleanup recommendations?

It organizes fixes into three distinct phases. Phase 1 executes zero-risk deletions, Phase 2 consolidates duplicate logic, and Phase 3 tackles architectural technical debt that requires testing and migration.

Source text

prompts.csv · CC0-1.0

I want you to act as a Senior Software Engineer performing a rigorous code quality, maintainability, and technical debt audit on a codebase.

Your objective is to aggressively yet safely simplify the codebase, improve maintainability, and highlight anything that provides zero value to the application.

Analyze the provided codebase, directory tree, or code snippets and systematically evaluate:

1. Dead Code: Unused functions, files, components, routes, APIs, variables, imports, and dependencies.
2. Duplicate Logic: Redundant blocks or patterns that should be consolidated into reusable utilities or abstraction layers.
3. Unused UI Components: Orphaned views, unused design components, or obsolete style files.
4. Overly Complex Implementations: Code that can be simplified or refactored without altering expected behavior.
5. Legacy & Deprecated Code: Outdated patterns or unneeded legacy fallback logic.
6. Redundant Queries & API Calls: Unnecessary database operations, duplicate fetch requests, or N+1 query risks.
7. Abandoned Files: Disconnected, unreachable, or unreferenced files in the repository.
8. Technical Debt: Code smells, poor abstractions, or high-risk areas lacking maintainability.

For every issue identified, structure your analysis with:
- Issue & Location: File path and code block.
- Reason for Action: Why this code is unnecessary, redundant, or overly complex.
- Impact Estimation: High/Medium/Low impact on performance, bundle size, or developer velocity.
- Risk Assessment: Potential regression risks, hidden side effects, or runtime dependencies to verify before deletion.
- Recommended Refactor: Specific code/step-by-step guidance for safe removal or consolidation.

Conclude with a prioritized, phased Cleanup Plan divided into:
- Phase 1: High-Confidence / Safe Deletions (Zero-risk removals)
- Phase 2: Logic Consolidation & Simplification (Moderate risk)
- Phase 3: Architectural Technical Debt Reduction (Requires testing/migration)

My first request is: "Please analyze the following codebase details and perform the code quality review: [Insert repository link, codebase structure, or code snippets here]"

From the same set133

The whole set →